Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[VL] Disable columnar table cache by default #3488

Merged
merged 7 commits into from
Nov 3, 2023
Merged

[VL] Disable columnar table cache by default #3488

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a52f7a3
diable columnar table cache
Oct 24, 2023
29da727
fix build
Oct 24, 2023
2d24ed4
retry use sys pros for enable columnar table cache test case by ulyss…
Nov 2, 2023
18268d5
Merge branch 'oap-project:main' into gayangya/disable_columnar_table_…
gaoyangxiaozhu Nov 2, 2023
d318f94
Merge branch 'oap-project:main' into gayangya/disable_columnar_table_…
gaoyangxiaozhu Nov 2, 2023
1debec0
disable columar table cache for spark34
Nov 3, 2023
a971e69
Merge branch 'oap-project:main' into gayangya/disable_columnar_table_…
gaoyangxiaozhu Nov 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion backends-velox/src/main/scala/io/glutenproject/backendsapi/velox/ListenerApiImpl.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ class ListenerApiImpl extends ListenerApi {

override def onDriverStart(conf: SparkConf): Unit = {
// sql table cache serializer
if (conf.getBoolean(GlutenConfig.COLUMNAR_TABLE_CACHE_ENABLED.key, defaultValue = true)) {
if (conf.getBoolean(GlutenConfig.COLUMNAR_TABLE_CACHE_ENABLED.key, defaultValue = false)) {
gaoyangxiaozhu marked this conversation as resolved.
Show resolved Hide resolved
conf.set(
StaticSQLConf.SPARK_CACHE_SERIALIZER.key,
"org.apache.spark.sql.execution.ColumnarCachedBatchSerializer")
Expand Down
1 change: 1 addition & 0 deletions backends-velox/src/test/scala/io/glutenproject/execution/VeloxColumnarCacheSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ class VeloxColumnarCacheSuite extends VeloxWholeStageTransformerSuite with Adapt
super.sparkConf
.set("spark.shuffle.manager", "org.apache.spark.shuffle.sort.ColumnarShuffleManager")
.set("spark.sql.shuffle.partitions", "3")
.set(GlutenConfig.COLUMNAR_TABLE_CACHE_ENABLED.key, "true")
}

private def checkColumnarTableCache(plan: SparkPlan): Unit = {
Expand Down
6 changes: 5 additions & 1 deletion gluten-ut/spark33/src/test/scala/org/apache/spark/sql/GlutenCachedTableSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@
*/
package org.apache.spark.sql

import io.glutenproject.GlutenConfig

import org.apache.spark.SparkConf
import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanHelper
import org.apache.spark.sql.execution.columnar.InMemoryRelation
Expand All @@ -24,9 +26,11 @@ class GlutenCachedTableSuite
extends CachedTableSuite
with GlutenSQLTestsTrait
with AdaptiveSparkPlanHelper {

// for temporarily disable the columnar table cache globally.
sys.props.put(GlutenConfig.COLUMNAR_TABLE_CACHE_ENABLED.key, "true")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

we should also do this for Spark3.4 which is merged recently

override def sparkConf: SparkConf = {
super.sparkConf.set("spark.sql.shuffle.partitions", "5")
super.sparkConf.set(GlutenConfig.COLUMNAR_TABLE_CACHE_ENABLED.key, "true")
}

test("GLUTEN - InMemoryRelation statistics") {
Expand Down
6 changes: 5 additions & 1 deletion gluten-ut/spark34/src/test/scala/org/apache/spark/sql/GlutenCachedTableSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@
*/
package org.apache.spark.sql

import io.glutenproject.GlutenConfig

import org.apache.spark.SparkConf
import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanHelper
import org.apache.spark.sql.execution.columnar.InMemoryRelation
Expand All @@ -24,9 +26,11 @@ class GlutenCachedTableSuite
extends CachedTableSuite
with GlutenSQLTestsTrait
with AdaptiveSparkPlanHelper {

// for temporarily disable the columnar table cache globally.
sys.props.put(GlutenConfig.COLUMNAR_TABLE_CACHE_ENABLED.key, "true")
override def sparkConf: SparkConf = {
super.sparkConf.set("spark.sql.shuffle.partitions", "5")
super.sparkConf.set(GlutenConfig.COLUMNAR_TABLE_CACHE_ENABLED.key, "true")
}

test("GLUTEN - InMemoryRelation statistics") {
Expand Down
2 changes: 1 addition & 1 deletion shims/common/src/main/scala/io/glutenproject/GlutenConfig.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -703,7 +703,7 @@ object GlutenConfig {
.internal()
.doc("Enable or disable columnar table cache.")
.booleanConf
.createWithDefault(true)
.createWithDefault(false)

val COLUMNAR_PHYSICAL_JOIN_OPTIMIZATION_THROTTLE =
buildConf("spark.gluten.sql.columnar.physicalJoinOptimizationLevel")
Expand Down
Loading